Training in progress, epoch 1

config.json

@@ -1,46 +1,46 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-tr-en",
+  "_name_or_path": "Helsinki-NLP/opus-tatoeba-en-tr",
   "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "activation_function": "swish",
   "architectures": [
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      57059
+      59993
     ]
   ],
   "bos_token_id": 0,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 57059,
-  "decoder_vocab_size": 57060,
+  "decoder_start_token_id": 59993,
+  "decoder_vocab_size": 59994,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
-  "eos_token_id": 43741,
-  "forced_eos_token_id": 43741,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "max_length": 512,
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_embedding": false,
-  "num_beams": 4,
+  "num_beams": 6,
   "num_hidden_layers": 6,
-  "pad_token_id": 57059,
+  "pad_token_id": 59993,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 57060
+  "vocab_size": 59994
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7ba0e20abfc55af2239670fae94657031fec449727e08737e0a06b7995cb1d
-size 939405120
+oid sha256:ceaabc8f8f4e2e14f49e831f44a6a6b6f9d3bf5cf53ae5cd29893077431c9d7c
+size 299690728

runs/Apr07_18-24-33_eb754cce07bd/events.out.tfevents.1712519502.eb754cce07bd.5646.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23704da73d27db17a0f067e5465a156db1ed92b9a4fe9d4ae7862422d3fc1c87
+size 401

runs/Apr07_20-46-56_eb754cce07bd/events.out.tfevents.1712522884.eb754cce07bd.5646.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b6258fb03d0ba00b5f9d2e1033db8d52292181c48cef692839587e2731bcc3
+size 5437

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "43741": {
+    "0": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "52508": {
+    "1": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "57059": {
+    "59993": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -31,9 +31,9 @@
   "pad_token": "<pad>",
   "return_tensors": "pt",
   "separate_vocabs": false,
-  "source_lang": "tr",
+  "source_lang": "eng",
   "sp_model_kwargs": {},
-  "target_lang": "en",
+  "target_lang": "tur",
   "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d402d873f4d992e26896c6bd5b77cd8b94bb6c9181a6c29225c11874f921f5
+oid sha256:cea6777cc439957cd7440afde80e403c8889b1a15b94bb71554f9a6aebf34fad
 size 5048